MLX
Safetensors
llama
prince-canuma's picture
97e1b600b8d963a9c8852a1b0d6613fecaf400ed314dc154c72680fae738a4d0
4b3b141 verified
|
raw
history blame
550 Bytes
metadata
license: apache-2.0
tags:
  - mlx

mlx-community/Yi-1.5-34B-Chat-8bit

The Model mlx-community/Yi-1.5-34B-Chat-8bit was converted to MLX format from 01-ai/Yi-1.5-34B-Chat using mlx-lm version 0.13.0.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Yi-1.5-34B-Chat-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)